run-llama

Multiple vector store integrations in run-llama/llama_index version v0.12.21 have SQL injection vulnerabilities.

An SQL injection vulnerability exists in the delete function of DuckDBVectorStore in run-llama/llama_index version v0.12.19.

A vulnerability in the FinanceChatLlamaPack of the run-llama/llama_index repository, versions up to v0.12.3, allows for SQL injection in the `run_sql_query` function of the `database_agent`.

A SQL injection vulnerability exists in the `duckdb_retriever` component of the run-llama/llama_index repository, specifically in the latest version.

A command injection vulnerability exists in the run-llama/llama_index repository, specifically within the safe_eval function.

LlamaIndex (aka llama_index) through 0.9.34 allows SQL injection via the Text-to-SQL feature in NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine, NLSQLRetriever, RetrieverQueryEngine, and PGVectorSQLQueryEngine.

LlamaIndex (run-llama/llama_index) versions up to and including 0.12.2 contain an uncontrolled resource consumption vulnerability in the VannaPack VannaQueryEngine implementation.

A path traversal vulnerability exists in run-llama/llama_index versions 0.12.27 through 0.12.40, specifically within the `encode_image` function in `generic_utils.py`.

An XML Entity Expansion vulnerability, also known as a 'billion laughs' attack, exists in the sitemap parser of the run-llama/llama_index repository, specifically affecting version v0.12.21.

A vulnerability in the `ObsidianReader` class of the run-llama/llama_index repository, versions 0.12.23 to 0.12.28, allows for arbitrary file read through symbolic links.

A Denial of Service (DoS) vulnerability has been identified in the KnowledgeBaseWebReader class of the run-llama/llama_index project, affecting version ~ latest(v0.12.15).

LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.load_from_disk() in llama_index/indices/managed/bge_m3/base.py.

A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack.

LLama-Index CLI version v0.12.20 contains an OS command injection vulnerability.

A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to version 0.12.28, involves the use of MD5 hashing to generate IDs for document chunks.

A critical deserialization vulnerability exists in the run-llama/llama_index library's JsonPickleSerializer component, affecting versions v0.12.27 through v0.12.40.

A vulnerability in the `default_jsonalyzer` function of the `JSONalyzeQueryEngine` in the run-llama/llama_index repository allows for SQL injection via prompt injection.

A vulnerability in the ArxivReader class of the run-llama/llama_index repository, versions up to v0.12.22.post1, allows for MD5 hash collisions when generating filenames for downloaded papers.

The JSONReader in run-llama/llama_index versions 0.12.28 is vulnerable to a stack overflow due to uncontrolled recursive JSON parsing.

A vulnerability in the ObsidianReader class of the run-llama/llama_index repository, specifically in version 0.12.27, allows for hardlink-based path traversal.

A vulnerability in the `KnowledgeBaseWebReader` class of the run-llama/llama_index repository, version latest, allows an attacker to cause a Denial of Service (DoS) by controlling a URL variable to contain the root URL.

A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs).

An issue was discovered in llama_index before 0.10.38.

The llama_index library version 0.12.33 sets the NLTK data directory to a subdirectory of the codebase by default, which is world-writable in multi-user environments.